Search for the global extremum using the correlation indicator for neural networks supervised learning

The article discusses the search for a global extremum in the training of artificial neural networks using a correlation indicator. A method based on a mathematical model of an artificial neural network presented as an information transmission system is proposed. Drawing attention to the fact that i...

সম্পূর্ণ বিবরণ

সংরক্ষণ করুন:

গ্রন্থ-পঞ্জীর বিবরন
প্রধান লেখক:	Vershkov, N. A., Вершков, Н. А., Babenko, M. G., Бабенко, М. Г., Kuchukov, V. A., Кучуков, В. А., Kuchukova, N. N., Кучукова, Н. Н.
বিন্যাস:	Статья
ভাষা:	English
প্রকাশিত:	Pleiades journals 2021
বিষয়গুলি:	Data communication systems Least squares approximations Comparative analysis Correlation function Effective analysis Neural networks
অনলাইন ব্যবহার করুন:	https://dspace.ncfu.ru/handle/20.500.12258/14736
ট্যাগগুলো:	ট্যাগ যুক্ত করুন কোনো ট্যাগ নেই, প্রথমজন হিসাবে ট্যাগ করুন!

id	ir-20.500.12258-14736
record_format	dspace
spelling	ir-20.500.12258-147362021-01-19T12:38:38Z Search for the global extremum using the correlation indicator for neural networks supervised learning Vershkov, N. A. Вершков, Н. А. Babenko, M. G. Бабенко, М. Г. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Data communication systems Least squares approximations Comparative analysis Correlation function Effective analysis Neural networks The article discusses the search for a global extremum in the training of artificial neural networks using a correlation indicator. A method based on a mathematical model of an artificial neural network presented as an information transmission system is proposed. Drawing attention to the fact that in information transmission systems widely used methods that allow effective analysis and recovery of useful signal against the background of various interferences: Gaussian, concentrated, pulsed, etc., it is possible to make an assumption about the effectiveness of the mathematical model of artificial neural network, presented as a system of information transmission. The article analyzes the convergence of training and experimentally obtained sequences based on a correlation indicator for fully-connected neural network. The possibility of estimating the convergence of the training and experimentally obtained sequences based on the joint correlation function as a measure of their energy similarity (difference) is confirmed. To evaluate the proposed method, a comparative analysis is made with the currently used indicators. The potential sources of errors in the least-squares method and the possibilities of the proposed indicator to overcome them are investigated. Simulation of the learning process of an artificial neural network has shown that the use of the joint correlation function together with the Adadelta optimizer allows us to get again in learning speed 2-3 times compared to CrossEntropyLoss 2021-01-19T12:17:09Z 2021-01-19T12:17:09Z 2020 Статья Vershkov, N., Babenko, M., Kuchukov, V., Kuchukova, N. Search for the global extremum using the correlation indicator for neural networks supervised learning // Programming and Computer Software. - 2020. - Volume 46. - Issue 8. - Pages 609-618 http://hdl.handle.net/20.500.12258/14736 en Programming and Computer Software application/pdf application/pdf Pleiades journals
institution	СКФУ
collection	Репозиторий
language	English
topic	Data communication systems Least squares approximations Comparative analysis Correlation function Effective analysis Neural networks
spellingShingle	Data communication systems Least squares approximations Comparative analysis Correlation function Effective analysis Neural networks Vershkov, N. A. Вершков, Н. А. Babenko, M. G. Бабенко, М. Г. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Search for the global extremum using the correlation indicator for neural networks supervised learning
description	The article discusses the search for a global extremum in the training of artificial neural networks using a correlation indicator. A method based on a mathematical model of an artificial neural network presented as an information transmission system is proposed. Drawing attention to the fact that in information transmission systems widely used methods that allow effective analysis and recovery of useful signal against the background of various interferences: Gaussian, concentrated, pulsed, etc., it is possible to make an assumption about the effectiveness of the mathematical model of artificial neural network, presented as a system of information transmission. The article analyzes the convergence of training and experimentally obtained sequences based on a correlation indicator for fully-connected neural network. The possibility of estimating the convergence of the training and experimentally obtained sequences based on the joint correlation function as a measure of their energy similarity (difference) is confirmed. To evaluate the proposed method, a comparative analysis is made with the currently used indicators. The potential sources of errors in the least-squares method and the possibilities of the proposed indicator to overcome them are investigated. Simulation of the learning process of an artificial neural network has shown that the use of the joint correlation function together with the Adadelta optimizer allows us to get again in learning speed 2-3 times compared to CrossEntropyLoss
format	Статья
author	Vershkov, N. A. Вершков, Н. А. Babenko, M. G. Бабенко, М. Г. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н.
author_facet	Vershkov, N. A. Вершков, Н. А. Babenko, M. G. Бабенко, М. Г. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н.
author_sort	Vershkov, N. A.
title	Search for the global extremum using the correlation indicator for neural networks supervised learning
title_short	Search for the global extremum using the correlation indicator for neural networks supervised learning
title_full	Search for the global extremum using the correlation indicator for neural networks supervised learning
title_fullStr	Search for the global extremum using the correlation indicator for neural networks supervised learning
title_full_unstemmed	Search for the global extremum using the correlation indicator for neural networks supervised learning
title_sort	search for the global extremum using the correlation indicator for neural networks supervised learning
publisher	Pleiades journals
publishDate	2021
url	https://dspace.ncfu.ru/handle/20.500.12258/14736
work_keys_str_mv	AT vershkovna searchfortheglobalextremumusingthecorrelationindicatorforneuralnetworkssupervisedlearning AT verškovna searchfortheglobalextremumusingthecorrelationindicatorforneuralnetworkssupervisedlearning AT babenkomg searchfortheglobalextremumusingthecorrelationindicatorforneuralnetworkssupervisedlearning AT babenkomg searchfortheglobalextremumusingthecorrelationindicatorforneuralnetworkssupervisedlearning AT kuchukovva searchfortheglobalextremumusingthecorrelationindicatorforneuralnetworkssupervisedlearning AT kučukovva searchfortheglobalextremumusingthecorrelationindicatorforneuralnetworkssupervisedlearning AT kuchukovann searchfortheglobalextremumusingthecorrelationindicatorforneuralnetworkssupervisedlearning AT kučukovann searchfortheglobalextremumusingthecorrelationindicatorforneuralnetworkssupervisedlearning
_version_	1760600251660500992

Search for the global extremum using the correlation indicator for neural networks supervised learning

অনুরূপ উপাদানগুলি